:orphan:

|rss_image|  **2021-05 - 1/1** :ref:`Blog <ap-main-0>` :ref:`benchmark (4) <ap-cat-benchmark-0>` :ref:`onnx (8) <ap-cat-onnx-0>`

.. |rss_image| image:: feed-icon-16x16.png
    :target: ../_downloads/rss.xml
    :alt: RSS

----


.. index:: 2021-05


.. _ap-month-2021-05-0:

2021-05 - 1/1
+++++++++++++

.. blogpostagg::
    :title: Numpy API for ONNX and scikit-learn (part II)
    :date: 2021-05-05
    :keywords: ONNX,API,numpy,scikit-learn
    :categories: API
    :rawfile: 2021/2021-05-05_numpyapionnx2.rst

    This follows blog post :ref:`Numpy API for ONNX and scikit-learn (part I)
    <blog-onnx-api-part1>`. It demonstrated how to insert a custom
    function in a pipeline and still be able to convert that pipeline
    into ONNX. This blog post shows how to implement a custom transformer.
    

    ...




.. blogpostagg::
    :title: Numpy API for ONNX and scikit-learn (part I)
    :date: 2021-05-05
    :keywords: ONNX,API,numpy,scikit-learn
    :categories: API
    :rawfile: 2021/2021-05-05_numpyapionnx1.rst

    :epkg:`sklearn-onnx` converts most of the pipelines including
    numerical preprocessing or predictors but it fails whenever
    custom code is involved. That covers the use of `FunctionTransformer
    <https://scikit-learn.org/stable/modules/generated/
    sklearn.preprocessing.FunctionTransformer.html>`_ or a new model
    inheriting from `BaseEstimator <https://scikit-learn.org/stable/
    modules/generated/sklearn.base.BaseEstimator.html>`_. To be successful,
    the conversion needs a way to convert the custom code into ONNX.
    The proposed solution here is bypass that complex steps
    (rewrite a python function with ONNX operators) by directly writing
    the custom code with ONNX operators. However, even though most of
    the operator are close to :epkg:`numpy` functions, they are not
    the same. To avoid spending time looking at them, many :epkg:`numpy`
    functions were implementing with ONNX operators. The custom function
    or predictor can then just be implemented with this API to build
    a unique ONNX graph executed with a runtime.
    

    ...





----

|rss_image|  **2021-05 - 1/1** :ref:`2021-08 (3) <ap-month-2021-08-0>` :ref:`2022-02 (1) <ap-month-2022-02-0>` :ref:`2022-05 (1) <ap-month-2022-05-0>` :ref:`2022-06 (1) <ap-month-2022-06-0>` :ref:`2022-11 (1) <ap-month-2022-11-0>`